-
SpatialThinker: Reinforcing 3D Reasoning in Multimodal LLMs via Spatial Rewards
Paper • 2511.07403 • Published • 14 -
hunarbatra/STVQA-7K
Viewer • Updated • 7.59k • 125 • 3 -
hunarbatra/SpatialThinker-3B
Image-Text-to-Text • 4B • Updated • 9 -
hunarbatra/SpatialThinker-7B
Image-Text-to-Text • 8B • Updated • 10
Hunar Batra PRO
hunarbatra
AI & ML interests
RL, Reasoning, Interpretability
Recent Activity
authored a paper 1 day ago
MCJudgeBench: A Benchmark for Constraint-Level Judge Evaluation in Multi-Constraint Instruction Following authored a paper 2 days ago
Towards Understanding Multimodal Fine-Tuning: Spatial Features